Anomaly Detection System

2. The anomaly detection system according to claim 1, wherein the dispersion of elements of the anomaly detection model is a variance of anomaly scores or an inter quartile range of elements of the anomaly detection model.

3. The anomaly detection system according to claim 1, wherein the means for learning anomaly detection models from the operation data set an initial anomaly detection model, and sequentially re-construct an anomaly detection model in which the dispersion of the anomaly scores is small from the anomaly detection model.

4. The anomaly detection system according to claim 1, wherein the anomaly detection model is an anomaly detection model based on the k-nearest neighbor distance.

5. The anomaly detection system according to claim 1, wherein, the means for learning anomaly detection models from the operation data generate, when generating a new anomaly detection model from a plurality of anomaly detection models, the new anomaly detection model by sampling the operation data from the plurality of anomaly detection models.

6. The anomaly detection system according to claim 1, including means for displaying a ratio of an anomaly score of the anomaly detection model in an initial state to an anomaly score of a re-constructed anomaly detection model.